eea2019_tp1_RiosPaez_GustavoArturo

TP1 EEA #Añadiendo las librerías necesarias

rm(list=ls())
library("dplyr")

Registered S3 method overwritten by 'dplyr':
  method           from
  print.rowwise_df     

Attaching package: 㤼㸱dplyr㤼㸲

The following objects are masked from 㤼㸱package:stats㤼㸲:

    filter, lag

The following objects are masked from 㤼㸱package:base㤼㸲:

    intersect, setdiff, setequal, union

library("tidyverse")

-- Attaching packages --------------------------------------- tidyverse 1.2.1 --
v ggplot2 3.2.1     v readr   1.3.1
v tibble  2.1.3     v purrr   0.3.2
v tidyr   1.0.0     v stringr 1.2.0
v ggplot2 3.2.1     v forcats 0.4.0
-- Conflicts ------------------------------------------ tidyverse_conflicts() --
x dplyr::filter() masks stats::filter()
x dplyr::lag()    masks stats::lag()

#1.Preparacion de los datos (I) #a.Leer el archivo ar_properties.csv y mostrar su estructura Leyendo el archivo usando read.table Luego usando Glipse para dar un vistazo a la DB t0, t1 y tcorridaCSV serán usados para medir el tiempo de lectura del archivo

t0       <-  Sys.time()
ar_properties <- read.table("ar_properties.csv",
                            sep=",",
                            dec=".",
                            header = TRUE,
                            fill = TRUE)

EOF within quoted string

t1       <-  Sys.time()
tcorridaCSV <-  as.numeric( t1 - t0, units = "secs")
glimpse(ar_properties)

Observations: 143,852
Variables: 24
$ id              <fct> S0we3z3V2JpHUJreqQ2t/w==, kMxcmAS8NvrynGBVbMOEaQ==, Ce3ojF+ZTOkB8...
$ ad_type         <fct> Propiedad, Propiedad, Propiedad, Propiedad, Propiedad, Propiedad,...
$ start_date      <fct> 2019-04-14, 2019-04-14, 2019-04-14, 2019-04-14, 2019-04-14, 2019-...
$ end_date        <fct> 2019-06-14, 2019-04-16, 9999-12-31, 9999-12-31, 2019-07-09, 2019-...
$ created_on      <fct> 2019-04-14, 2019-04-14, 2019-04-14, 2019-04-14, 2019-04-14, 2019-...
$ lat             <fct> -34.9433118208, -34.63181, NA, -34.65470505, -34.65494919, -32.93...
$ lon             <fct> -54.9296557586, -58.420599, NA, -58.79089355, -58.787117, -60.683...
$ l1              <fct> Uruguay, Argentina, Argentina, Argentina, Argentina, Argentina, A...
$ l2              <fct> Maldonado, Capital Federal, Bs.As. G.B.A. Zona Norte, Bs.As. G.B....
$ l3              <fct> Punta del Este, Boedo, NA, Moreno, Moreno, Rosario, Ituzaingó, J...
$ l4              <fct> NA, NA, NA, Moreno, Moreno, NA, Ituzaingó, NA, NA, NA, NA, NA, N...
$ l5              <fct> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N...
$ l6              <fct> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N...
$ rooms           <fct> 2, NA, 2, 2, 2, 4, NA, 6, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,...
$ bedrooms        <fct> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N...
$ bathrooms       <fct> 1, NA, 1, 2, 3, 1, 3, 3, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, ...
$ surface_total   <fct> 45, NA, 200, 460, 660, NA, 70, NA, 1300, 405, 352, 373, 360, 1325...
$ surface_covered <fct> 40, NA, NA, 100, 148, 89, 122, NA, NA, NA, NA, NA, NA, 2, NA, NA,...
$ price           <fct> 13000, 0, NA, NA, NA, NA, NA, NA, 0, NA, 0, NA, NA, NA, NA, NA, 0...
$ currency        <fct> UYU, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, ...
$ price_period    <fct> Mensual, Mensual, NA, Mensual, Mensual, Mensual, Mensual, Mensual...
$ title           <fct> Departamento - Roosevelt, PH - Boedo, Ituzaingo  1100 - $ 1 - Cas...
$ property_type   <fct> Departamento, PH, Casa, Casa, Casa, Casa, Casa, Casa, Lote, Lote,...
$ operation_type  <fct> Alquiler, Venta, Alquiler, Venta, Venta, Venta, Venta, Alquiler, ...

#b.Quedarse con aquellos registros que: # i.Pertenecen a Argentina y Capital Federal # ii.Cuyo precio esta en dolares (USD) # iii.El tipo de propiedad sea: Departamento, PH o Casa # iv.El tipo de operacion sea Venta #Revisé la variable Currency para ver si todas estaban marcadas por USD para dolaers #Revisé los NA en country l1 #Deperatamento 42041 #PH 4564 #Casa 21535 #Sólo por el filtro de “Capital Federal” tenemos 47577

ar_properties_filtrado <- ar_properties %>% filter(l1 == "Argentina", l2 == "Capital Federal",
                                                   currency == "USD" ,
                                                   property_type %in% c("Casa","PH", "Departamento"),
                                                   operation_type == "Venta")

glimpse(ar_properties_filtrado)

Observations: 24,323
Variables: 24
$ id              <fct> oyj+f764ALCYodIqBvWAww==, HdjpKrqdwYfH9YU1DKjltg==, YwWE3rTb2+gms...
$ ad_type         <fct> Propiedad, Propiedad, Propiedad, Propiedad, Propiedad, Propiedad,...
$ start_date      <fct> 2019-04-14, 2019-04-14, 2019-04-14, 2019-04-14, 2019-04-14, 2019-...
$ end_date        <fct> 2019-07-10, 2019-04-15, 2019-06-30, 9999-12-31, 2019-05-21, 9999-...
$ created_on      <fct> 2019-04-14, 2019-04-14, 2019-04-14, 2019-04-14, 2019-04-14, 2019-...
$ lat             <fct> -34.6522498, -34.6282483, -34.5927955, -34.56563187, -34.62217712...
$ lon             <fct> -58.385565, -58.4065245, -58.4209298, -58.46513367, -58.52272415,...
$ l1              <fct> Argentina, Argentina, Argentina, Argentina, Argentina, Argentina,...
$ l2              <fct> Capital Federal, Capital Federal, Capital Federal, Capital Federa...
$ l3              <fct> Barracas, Boedo, Palermo, Belgrano, Versalles, Velez Sarsfield, N...
$ l4              <fct> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N...
$ l5              <fct> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N...
$ l6              <fct> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N...
$ rooms           <fct> NA, 6, NA, 3, NA, 3, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 3,...
$ bedrooms        <fct> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N...
$ bathrooms       <fct> NA, 2, 2, 4, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 1...
$ surface_total   <fct> 300, 178, 240, 157, 140, 95, 44, 40, 49, 40, 40, 40, 49, 40, 23, ...
$ surface_covered <fct> 180, 240, 157, NA, 110, 69, 38, 37, 44, 37, 37, 37, 44, 37, 23, 3...
$ price           <fct> 320000, 500000, 350000, 470000, 155000, 199900, 147000, 92294, 11...
$ currency        <fct> USD, USD, USD, USD, USD, USD, USD, USD, USD, USD, USD, USD, USD, ...
$ price_period    <fct> Mensual, Mensual, Mensual, NA, NA, NA, Mensual, Mensual, Mensual,...
$ title           <fct> "PH EN VENTA", "Casa - San Telmo", "CASA EN VENTA", "Mendoza  320...
$ property_type   <fct> PH, Casa, Casa, Casa, Casa, Casa, Departamento, Departamento, Dep...
$ operation_type  <fct> Venta, Venta, Venta, Venta, Venta, Venta, Venta, Venta, Venta, Ve...

#c.Seleccionar las variables id, l3, rooms, bedrooms, bathrooms, surface_total, surface_covered, price y property_type

ar_properties_filtrado <- ar_properties_filtrado %>% 
  select(id, l3, rooms, bedrooms, bathrooms, surface_total, surface_covered, price, property_type)
glimpse(ar_properties_filtrado)

Observations: 24,323
Variables: 9
$ id              <fct> oyj+f764ALCYodIqBvWAww==, HdjpKrqdwYfH9YU1DKjltg==, YwWE3rTb2+gms...
$ l3              <fct> Barracas, Boedo, Palermo, Belgrano, Versalles, Velez Sarsfield, N...
$ rooms           <fct> NA, 6, NA, 3, NA, 3, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 3,...
$ bedrooms        <fct> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N...
$ bathrooms       <fct> NA, 2, 2, 4, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 1...
$ surface_total   <fct> 300, 178, 240, 157, 140, 95, 44, 40, 49, 40, 40, 40, 49, 40, 23, ...
$ surface_covered <fct> 180, 240, 157, NA, 110, 69, 38, 37, 44, 37, 37, 37, 44, 37, 23, 3...
$ price           <fct> 320000, 500000, 350000, 470000, 155000, 199900, 147000, 92294, 11...
$ property_type   <fct> PH, Casa, Casa, Casa, Casa, Casa, Departamento, Departamento, Dep...

#2.Analisis exploratorios (I) #a.Obtener la cantidad de valores unicos y de valores faltantes (NAs) para cada una de estas variables #Para esto usaremos la función ‘unique’

unique(ar_properties_filtrado)

#Pero con apply la podemos aplicar a todo el dataFrame sin duplicar código
uniqueValues <- apply(ar_properties_filtrado,2,unique)
#Tenemos como resultado:
uniqueValues$l3

 [1] "Barracas"             "Boedo"                "Palermo"             
 [4] "Belgrano"             "Versalles"            "Velez Sarsfield"     
 [7] "Nuñez"               "Almagro"              "Caballito"           
[10] "Catalinas"            "San Telmo"            "Villa Crespo"        
[13] "Puerto Madero"        "Villa Urquiza"        "Parque Chacabuco"    
[16] "Retiro"               "Floresta"             "Recoleta"            
[19] "Saavedra"             "Balvanera"            "Colegiales"          
[22] "Parque Chas"          "Barrio Norte"         "Villa Devoto"        
[25] "Villa Ortuzar"        "Villa Pueyrredón"    "Paternal"            
[28] "Villa Real"           "Once"                 "Flores"              
[31] "Las Cañitas"         "Villa Santa Rita"     "Centro / Microcentro"
[34] "Villa del Parque"     "Parque Centenario"    "Congreso"            
[37] "Parque Avellaneda"    "Chacarita"            "Abasto"              
[40] "San Cristobal"        "Boca"                 "Liniers"             
[43] "Villa General Mitre"  "Agronomía"           "Parque Patricios"    
[46] "Coghlan"              "Monserrat"            "San Nicolás"        
[49] "Villa Lugano"         NA                     "Constitución"       
[52] "Mataderos"            "Monte Castro"         "Villa Luro"          
[55] "Pompeya"              "Tribunales"           "Villa Soldati"       
[58] "Villa Riachuelo"     

#l3 -57 Barrios entontrados y NA
uniqueValues$rooms

 [1] NA   "6"  "3"  "1"  "2"  "5"  "4"  "7"  "8"  "9"  "10" "12" "11" "15" "26" "32" "17" "20"

#rooms 17 categorías (y NA) sin embargo se tienen valores que no tienen mucho sentido
#Algunos de ellos parecieran ser excesivos
uniqueValues$bedrooms

 [1] NA    "0"   "1"   "2"   "3"   "4"   "5"   "7"   "6"   "8"   "16"  "9"   "25"  "130" "10" 
[16] "13"  "11" 

#bedrooms 17 categorías (y NA) se tiene un outlier de 130 que debería ser un error de tipeo
#dado que en rooms no tenemos ningún outlier que se le acerque
uniqueValues$bathrooms

 [1] NA   "2"  "4"  "1"  "3"  "5"  "7"  "6"  "10" "9"  "8"  "13" "14"

#bathrooms 12 categorías (y NA) los valores más grandes son llamativos
uniqueValues$surface_total

  [1] "300"    "178"    "240"    "157"    "140"    "95"     "44"     "40"     "49"    
 [10] "23"     "32"     "36"     "90"     "45"     "54"     "33"     "59"     "55"    
 [19] "127"    "38"     "174"    "75"     "70"     "31"     "48"     "53"     "39"    
 [28] "58"     "42"     "52"     "64"     "50"     "83"     "41"     "29"     "69"    
 [37] "43"     "84"     "62"     "63"     "60"     "100"    "170"    "5821"   "96"    
 [46] "187"    "110"    "68"     "78"     "76"     "113"    "92"     "67"     "97"    
 [55] "150"    "197"    "80"     "184"    "133"    "108"    "91"     "77"     "190"   
 [64] "85"     "180"    NA       "94"     "128"    "277"    "111"    "202"    "317"   
 [73] "640"    "1309"   "503"    "320"    "360"    "125"    "120"    "26"     "81"    
 [82] "56"     "220"    "65"     "28"     "25"     "35"     "160"    "27"     "115"   
 [91] "66"     "37"     "103"    "79"     "47"     "34"     "82"     "87"     "72"    
[100] "112"    "200"    "230"    "74"     "71"     "89"     "143"    "102"    "165"   
[109] "166"    "280"    "710"    "411"    "185"    "223"    "273"    "126"    "99"    
[118] "260"    "98"     "154"    "213"    "136"    "158"    "270"    "144"    "420"   
[127] "210"    "462"    "175"    "612"    "269"    "142"    "219"    "105"    "107"   
[136] "135"    "244"    "322"    "225"    "374"    "109"    "233"    "30"     "22"    
[145] "106"    "440"    "24"     "148"    "20"     "86"     "73"     "61"     "130"   
[154] "88"     "46"     "173"    "370"    "276"    "207"    "51"     "146"    "131"   
[163] "93"     "57"     "312"    "457"    "21"     "129"    "242"    "363"    "114"   
[172] "104"    "101"    "134"    "182"    "198"    "250"    "340"    "118"    "161"   
[181] "217"    "179"    "124"    "298"    "425"    "371"    "562"    "212"    "196"   
[190] "286"    "400"    "159"    "355"    "430"    "284"    "315"    "330"    "336"   
[199] "386"    "350"    "384"    "177"    "123"    "141"    "119"    "183"    "138"   
[208] "155"    "239"    "122"    "195"    "338"    "238"    "249"    "335"    "117"   
[217] "394"    "304"    "214"    "241"    "215"    "145"    "253"    "116"    "402"   
[226] "235"    "407"    "194"    "224"    "264"    "409"    "216"    "508"    "601"   
[235] "139"    "523"    "405"    "431"    "132"    "171"    "246"    "248"    "271"   
[244] "19"     "162"    "152"    "258"    "10145"  "228"    "203"    "164"    "181"   
[253] "121"    "337"    "186"    "188"    "156"    "192"    "147"    "500"    "231"   
[262] "255"    "380"    "168"    "153"    "193"    "331"    "172"    "149"    "550"   
[271] "278"    "532"    "352"    "167"    "347"    "390"    "189"    "436"    "910"   
[280] "279"    "287"    "15"     "191"    "199"    "2948"   "169"    "262"    "288"   
[289] "259"    "245"    "290"    "533"    "204"    "658"    "305"    "222"    "289"   
[298] "205"    "254"    "275"    "765"    "445"    "265"    "332"    "388"    "306"   
[307] "364"    "359"    "16"     "399"    "163"    "308"    "327"    "395"    "252"   
[316] "236"    "303"    "345"    "464"    "495"    "600"    "14"     "3935"   "309"   
[325] "211"    "201"    "243"    "232"    "299"    "297"    "510"    "580"    "392"   
[334] "1216"   "650"    "540"    "285"    "385"    "17"     "137"    "3608"   "637"   
[343] "616"    "11250"  "302"    "634"    "375"    "1000"   "950"    "151"    "251"   
[352] "206"    "624"    "1112"   "413"    "226"    "227"    "263"    "176"    "437"   
[361] "406"    "422"    "719"    "598"    "610"    "261"    "291"    "307"    "377"   
[370] "234"    "750"    "310"    "325"    "281"    "268"    "256"    "535"    "880"   
[379] "450"    "745"    "1050"   "293"    "294"    "372"    "296"    "339"    "401"   
[388] "567"    "570"    "221"    "5647"   "486"    "343"    "492"    "348"    "283"   
[397] "444"    "313"    "850"    "737"    "301"    "208"    "361"    "522"    "326"   
[406] "397"    "257"    "362"    "677"    "483"    "328"    "455"    "356"    "351"   
[415] "490"    "945"    "18"     "274"    "229"    "489"    "342"    "602"    "267"   
[424] "470"    "0"      "475"    "237"    "473"    "820"    "282"    "465"    "2000"  
[433] "292"    "314"    "410"    "382"    "126062" "516"    "858"    "487"    "481"   
[442] "5322"   "453"    "560"    "781"    "329"    "379"    "730"    "318"    "780"   
[451] "460"    "354"    "424"    "515"    "847"    "800"    "536"    "502"    "266"   
[460] "295"    "341"    "6085"   "272"    "524"    "649"    "324"    "700"    "334"   
[469] "632"    "358"    "1200"   "16725"  "247"    "12"     "529"    "609"    "525"   
[478] "451"    "446"    "995"    "323"    "568"    "494"    "537"    "6905"   "576"   
[487] "396"    "209"    "311"    "654"    "346"    "9053"   "378"    "615"    "480"   
[496] "621"    "417"    "1060"   "13"     "593"    "387"    "6845"   "376"    "726"   
[505] "672"    "218"    "518"    "447"    "630"    "365"    "591"    "506"    "853"   
[514] "554"    "389"    "520"    "373"    "590"    "715"    "426"    "521"    "383"   
[523] "534"    "783"    "435"    "545"    "962"    "1400"   "900"    "6600"   "2773"  
[532] "4534"   "526"    "391"    "923"    "367"    "736"    "398"    "4500"  

uniqueValues$surface_covered

  [1] "180"    "240"    "157"    NA       "110"    "69"     "38"     "37"     "44"    
 [10] "23"     "30"     "34"     "33"     "90"     "35"     "48"     "40"     "32"    
 [19] "41"     "36"     "55"     "127"    "174"    "29"     "68"     "70"     "28"    
 [28] "50"     "58"     "60"     "54"     "39"     "65"     "47"     "31"     "49"    
 [37] "57"     "45"     "100"    "73"     "120"    "53"     "96"     "91"     "187"   
 [46] "77"     "56"     "63"     "66"     "62"     "46"     "103"    "101"    "80"    
 [55] "72"     "112"    "93"     "74"     "178"    "133"    "87"     "129"    "85"    
 [64] "81"     "171"    "145"    "76"     "94"     "234"    "75"     "95"     "170"   
 [73] "123"    "288"    "420"    "1000"   "192"    "450"    "300"    "128"    "26"    
 [82] "220"    "25"     "59"     "148"    "27"     "52"     "67"     "105"    "4"     
 [91] "43"     "150"    "230"    "84"     "89"     "83"     "135"    "61"     "78"    
[100] "140"    "102"    "265"    "185"    "200"    "160"    "107"    "130"    "115"   
[109] "92"     "244"    "152"    "213"    "64"     "225"    "121"    "158"    "175"   
[118] "182"    "250"    "395"    "210"    "328"    "163"    "1"      "286"    "688"   
[127] "264"    "143"    "214"    "97"     "149"    "104"    "189"    "233"    "22"    
[136] "51"     "99"     "406"    "21"     "17"     "71"     "42"     "79"     "108"   
[145] "125"    "380"    "146"    "98"     "249"    "165"    "114"    "18"     "24"    
[154] "147"    "19"     "86"     "154"    "172"    "137"    "162"    "118"    "136"   
[163] "119"    "139"    "195"    "173"    "266"    "310"    "144"    "196"    "263"   
[172] "205"    "155"    "372"    "169"    "315"    "142"    "190"    "255"    "330"   
[181] "138"    "386"    "350"    "126"    "82"     "295"    "177"    "166"    "106"   
[190] "111"    "124"    "159"    "132"    "277"    "280"    "238"    "117"    "394"   
[199] "270"    "151"    "304"    "134"    "227"    "232"    "184"    "251"    "374"   
[208] "194"    "275"    "259"    "409"    "340"    "260"    "355"    "400"    "88"    
[217] "453"    "161"    "331"    "226"    "109"    "20"     "390"    "203"    "10145" 
[226] "211"    "186"    "188"    "156"    "141"    "500"    "215"    "122"    "191"   
[235] "164"    "116"    "198"    "193"    "357"    "312"    "113"    "332"    "183"   
[244] "342"    "181"    "550"    "294"    "217"    "287"    "15"     "199"    "2948"  
[253] "2667"   "131"    "291"    "271"    "285"    "153"    "540"    "345"    "248"   
[262] "418"    "257"    "16"     "282"    "242"    "218"    "258"    "212"    "228"   
[271] "14"     "3935"   "176"    "352"    "231"    "279"    "432"    "338"    "946"   
[280] "650"    "385"    "290"    "219"    "576"    "252"    "8830"   "341"    "700"   
[289] "206"    "167"    "491"    "750"    "413"    "302"    "216"    "437"    "422"   
[298] "425"    "320"    "408"    "335"    "600"    "322"    "370"    "360"    "179"   
[307] "12"     "197"    "276"    "325"    "267"    "268"    "880"    "297"    "209"   
[316] "745"    "870"    "293"    "246"    "202"    "296"    "313"    "401"    "306"   
[325] "567"    "388"    "8"      "207"    "435"    "245"    "281"    "3"      "444"   
[334] "440"    "10"     "460"    "508"    "239"    "208"    "308"    "261"    "262"   
[343] "236"    "243"    "362"    "568"    "483"    "168"    "356"    "235"    "339"   
[352] "344"    "201"    "317"    "845"    "274"    "278"    "421"    "224"    "820"   
[361] "1400"   "126062" "560"    "6770"   "448"    "5322"   "414"    "222"    "412"   
[370] "237"    "530"    "229"    "354"    "319"    "324"    "378"    "301"    "391"   
[379] "800"    "375"    "506"    "273"    "2708"   "3308"   "5821"   "8080"   "377"   
[388] "3506"   "272"    "397"    "347"    "570"    "379"    "371"    "269"    "303"   
[397] "307"    "1200"   "247"    "254"    "256"    "457"    "478"    "438"    "309"   
[406] "519"    "323"    "298"    "532"    "8050"   "559"    "486"    "580"    "221"   
[415] "204"    "253"    "623"    "327"    "424"    "980"    "314"    "472"    "5930"  
[424] "6756"   "376"    "442"    "475"    "292"    "652"    "5"      "7"      "284"   
[433] "366"    "436"    "326"    "353"    "630"    "336"    "430"    "334"    "455"   
[442] "715"    "426"    "318"    "361"    "383"    "321"    "363"    "384"    "470"   
[451] "902"    "850"    "1978"   "590"    "431"    "2773"   "1033"   "867"    "526"   
[460] "410"    "641"   

#surface_total y surface_covered alta variabilidad, dado que es una variable numérica, 
#se podría transformar en categórica revisando más a fondo los valores
summary(as.integer(uniqueValues$surface_total))

    Min.  1st Qu.   Median     Mean  3rd Qu.     Max.     NA's 
     0.0    145.2    279.5    749.6    450.8 126062.0        1 

summary(as.integer(uniqueValues$surface_covered))

    Min.  1st Qu.   Median     Mean  3rd Qu.     Max.     NA's 
     1.0    120.8    236.5    719.7    374.2 126062.0        1 

#Price
uniqueValues$price

   [1] "320000"  "500000"  "350000"  "470000"  "155000"  "199900"  "147000"  "92294"  
   [9] "115000"  "77000"   "88900"   "88798"   "110975"  "92943"   "69000"   "99000"  
  [17] "96984"   "125000"  "99500"   "121600"  "285000"  "150000"  "140000"  "110000" 
  [25] "96000"   "248200"  "152732"  "310000"  "108000"  "94800"   "1080000" "88000"  
  [33] "225000"  "85000"   "129900"  "185000"  "158000"  "98000"   "80000"   "159900" 
  [41] "87000"   "178000"  "172000"  "208000"  "83000"   "134000"  "135000"  "105000" 
  [49] "165000"  "90000"   "104500"  "119000"  "192000"  "390000"  "169000"  "86000"  
  [57] "79000"   "315000"  "230000"  "120000"  "259000"  "180000"  "269900"  "190000" 
  [65] "175000"  "130000"  "209000"  "270000"  "340000"  "194500"  "255000"  "139000" 
  [73] "439000"  "729000"  "128000"  "101000"  "92000"   "245000"  "214900"  "200000" 
  [81] "385000"  "370000"  "220000"  "189000"  "239000"  "260000"  "252000"  "290000" 
  [89] "790000"  "595000"  "280000"  "195000"  "613567"  "215000"  "210000"  "580000" 
  [97] "224000"  "850000"  "680000"  "1115000" "900000"  "250000"  "199000"  "249000" 
 [105] "94000"   "95000"   "70000"   "65000"   "795000"  "325000"  "182000"  "183000" 
 [113] "380000"  "770000"  "68000"   "84000"   "160000"  "100700"  "102000"  "168000" 
 [121] "855000"  "865000"  "485000"  "780000"  "75000"   "106000"  "142000"  "235000" 
 [129] "510000"  "103000"  "98500"   "104000"  "187300"  "123900"  "128400"  "85600"  
 [137] "80400"   "193000"  "195200"  "126400"  "92400"   "191200"  "136500"  "305000" 
 [145] "720000"  "107000"  "74000"   "54900"   "109000"  "145000"  "143000"  "116000" 
 [153] "204000"  "100000"  "239800"  "93000"   "205000"  "138000"  "112000"  "360000" 
 [161] "124000"  "170000"  "84102"   "127000"  "111000"  "173000"  "217000"  "152000" 
 [169] "149000"  "286000"  "995000"  "275000"  "206700"  "490000"  "268000"  "295000" 
 [177] "460000"  "650000"  "980000"  "440000"  "384000"  "450000"  "1700000" "397000" 
 [185] "550000"  "620000"  "184000"  "1850000" "1650000" "375000"  "540000"  "1300000"
 [193] "1970000" "1250000" "399000"  "628000"  "1150000" "1350000" "1600000" "297000" 
 [201] "278000"  "332000"  "133000"  "479000"  "365000"  "355000"  "240000"  "649000" 
 [209] "420000"  "236000"  "264000"  "300000"  "749000"  "84500"   "69500"   "97800"  
 [217] "415000"  "73000"   "82000"   "132000"  "138500"  "419000"  "1200000" "64900"  
 [225] "445000"  "359500"  "239500"  "206000"  "282000"  "118000"  "89000"   "198000" 
 [233] "129000"  "78000"   "299000"  "111900"  "192900"  "64000"   "318000"  "174000" 
 [241] "157354"  "108286"  "99900"   "219000"  "42000"   "329000"  "895000"  "149500" 
 [249] "157800"  "137000"  "520000"  "1100000" "144900"  "398000"  "124999"  "157500" 
 [257] "117000"  "378000"  "191911"  "289000"  "37000"   "345000"  "518000"  "83500"  
 [265] "395000"  "430000"  "269000"  "49000"   "114000"  "99800"   "114500"  "90500"  
 [273] "128500"  "241500"  "62000"   "203788"  "211011"  "194400"  "45000"   "95266"  
 [281] "85178"   "93989"   "95832"   "88372"   "93374"   "83370"   "92479"   "87341"  
 [289] "98428"   "91602"   "98930"   "90040"   "90766"   "91707"   "99518"   "84274"  
 [297] "94192"   "89054"   "101360"  "86106"   "89770"   "97098"   "102214"  "100762" 
 [305] "94474"   "97675"   "85037"   "90857"   "92146"   "86705"   "95904"   "97192"  
 [313] "100321"  "85629"   "83916"   "104106"  "81703"   "95809"   "96535"   "94642"  
 [321] "141000"  "159000"  "55000"   "103300"  "89900"   "135300"  "284000"  "97000"  
 [329] "170052"  "162400"  "330000"  "123000"  "84900"   "368000"  "314200"  "410000" 
 [337] "144500"  "177000"  "302797"  "276404"  "288569"  "277564"  "97500"   "244290" 
 [345] "162505"  "248081"  "203000"  "67500"   "88500"   "212500"  "159500"  "79900"  
 [353] "670000"  "298000"  "572000"  "404000"  "126900"  "239999"  "1000000" "232000" 
 [361] "480000"  "364000"  "400000"  "186000"  "353000"  "335000"  "307000"  "265000" 
 [369] "342000"  "218000"  "227000"  "228000"  "279900"  "242000"  "149600"  "169900" 
 [377] "254000"  "153000"  "235500"  "52000"   "176000"  "179000"  "189900"  "575000" 
 [385] "249999"  "154900"  "744000"  "886000"  "349000"  "449900"  "387000"  "590000" 
 [393] "549000"  "212000"  "304500"  "495000"  "920000"  "3500000" "515000"  "750000" 
 [401] "3400000" "690000"  "640000"  "698000"  "880000"  "565000"  "598000"  "144000" 
 [409] "156000"  "194900"  "95500"   "237000"  "156960"  "294000"  "162000"  "72000"  
 [417] "160125"  "59900"   "95200"   "109500"  "119500"  "113000"  "35000"   "475000" 
 [425] "125900"  "173583"  "99100"   "122500"  "372000"  "168900"  "226000"  "630000" 
 [433] "163000"  "350550"  "279000"  "493000"  "449000"  "309000"  "57900"   "870000" 
 [441] "563000"  "194000"  "319000"  "465000"  "615000"  "229000"  "2550000" "3700000"
 [449] "1480000" "940000"  "860000"  "359100"  "448000"  "343000"  "719000"  "444000" 
 [457] "828000"  "455000"  "267000"  "524000"  "148000"  "435000"  "2900000" "950000" 
 [465] "4500000" "675000"  "530000"  "560000"  "47000"   "425000"  "93500"   "58174"  
 [473] "75542"   "98280"   "95280"   "730000"  "187000"  "570000"  "122000"  "157000" 
 [481] "145600"  "149900"  "825000"  "1140000" "1400000" "1050000" "625000"  "164000" 
 [489] "60000"   "890000"  "427696"  "712000"  "85720"   "133849"  "59000"   "106800" 
 [497] "119700"  "116800"  "118600"  "114800"  "102700"  "113800"  "76000"   "313000" 
 [505] "74500"   "745900"  "84501"   "120150"  "197860"  "190250"  "115700"  "119900" 
 [513] "185080"  "103320"  "50000"   "89999"   "73900"   "186600"  "133500"  "105100" 
 [521] "597000"  "158900"  "136422"  "803648"  "627880"  "129294"  "2169696" "69900"  
 [529] "127800"  "60500"   "64800"   "105948"  "99573"   "148300"  "106948"  "133900" 
 [537] "156890"  "76900"   "164198"  "248000"  "635000"  "229900"  "164600"  "147500" 
 [545] "199500"  "202375"  "233000"  "229500"  "367000"  "158500"  "158250"  "217500" 
 [553] "177600"  "279500"  "166000"  "39500"   "37500"   "216000"  "289100"  "244900" 
 [561] "4000000" "224900"  "287000"  "369000"  "897000"  "1500000" "1550000" "1800000"
 [569] "1380000" "223000"  "4800000" "2800000" "351000"  "845000"  "660000"  "699000" 
 [577] "1680000" "188000"  "87749"   "257000"  "189500"  "202566"  "198432"  "210834" 
 [585] "215488"  "214968"  "45900"   "166600"  "90800"   "81000"   "2345678" "124500" 
 [593] "167000"  "316484"  "262000"  "126825"  "139500"  "131100"  "110600"  "1234567"
 [601] "121000"  "74900"   "56000"   "169500"  "134800"  "109900"  "61000"   "80047"  
 [609] "77553"   "77500"   "89800"   "346000"  "1030000" "559000"  "591361"  "558571" 
 [617] "68500"   "75500"   "65500"   "72500"   "85500"   "79500"   "64500"   "71000"  
 [625] "89500"   "66500"   "73500"   "43000"   "63000"   "76500"   "58500"   "82500"  
 [633] "62500"   "80500"   "92500"   "56500"   "59500"   "70500"   "91650"   "101050" 
 [641] "725000"  "104436"  "115788"  "64212"   "118463"  "44592"   "69258"   "67241"  
 [649] "92818"   "90804"   "47294"   "61993"   "134725"  "156188"  "55517"   "58237"  
 [657] "49135"   "136000"  "66000"   "112400"  "138600"  "153500"  "201500"  "66900"  
 [665] "83800"   "133575"  "147275"  "193500"  "122900"  "86130"   "101039"  "181140" 
 [673] "148200"  "109800"  "102573"  "93600"   "104948"  "64950"   "990000"  "1390000"
 [681] "1340000" "184300"  "272000"  "174900"  "119990"  "389000"  "496000"  "228542" 
 [689] "387090"  "359000"  "292000"  "249500"  "238000"  "452000"  "1360000" "1450000"
 [697] "260850"  "459000"  "545000"  "519000"  "3000000" "1099000" "296000"  "128900" 
 [705] "535000"  "80711"   "79120"   "371000"  "81900"   "32000"   "102526"  "102481" 
 [713] "104311"  "112587"  "87500"   "39000"   "104900"  "67000"   "179500"  "126000" 
 [721] "442650"  "476700"  "499800"  "284997"  "374000"  "695000"  "408400"  "196000" 
 [729] "314000"  "151000"  "882700"  "781820"  "819650"  "807040"  "794430"  "197000" 
 [737] "258000"  "321000"  "1750000" "338000"  "910000"  "318200"  "738400"  "875000" 
 [745] "555000"  "423300"  "91500"   "998000"  "428000"  "243000"  "154000"  "389500" 
 [753] "68100"   "108500"  "129500"  "73600"   "108700"  "79200"   "60200"   "106600" 
 [761] "27900"   "175800"  "139900"  "110900"  "399900"  "124900"  "211000"  "915000" 
 [769] "166900"  "327000"  "610000"  "1620000" "3089000" "2490000" "700000"  "1195000"
 [777] "1440000" "1545000" "1730000" "69800"   "138900"  "86500"   "247000"  "57000"  
 [785] "405000"  "142900"  "91900"   "85900"   "180380"  "151287"  "209500"  "131990" 
 [793] "339000"  "115900"  "82900"   "184980"  "179900"  "214000"  "183400"  "49900"  
 [801] "599000"  "1490000" "348000"  "1950000" "51500"   "144800"  "159300"  "145800" 
 [809] "289500"  "159700"  "134900"  "241400"  "830000"  "186070"  "86600"   "114900" 
 [817] "476000"  "91000"   "26500"   "191990"  "124990"  "106150"  "100760"  "1395000"
 [825] "1604320" "129981"  "106900"  "97900"   "122845"  "110935"  "94900"   "202000" 
 [833] "265500"  "390250"  "407000"  "710000"  "394000"  "498000"  "685000"  "112500" 
 [841] "336000"  "261000"  "277000"  "2500000" "2300000" "960000"  "1090000" "166400" 
 [849] "107900"  "78500"   "131000"  "141050"  "100580"  "73295"   "94160"   "125653" 
 [857] "118500"  "357000"  "698900"  "975000"  "760000"  "58000"   "255982"  "95770"  
 [865] "201370"  "134016"  "101516"  "108216"  "139454"  "103695"  "102215"  "105216" 
 [873] "89700"   "100070"  "140003"  "148539"  "146078"  "126246"  "142473"  "145212" 
 [881] "134006"  "136016"  "55500"   "79600"   "71662"   "319500"  "712600"  "379000" 
 [889] "79750"   "73402"   "80892"   "74965"   "76560"   "78155"   "81345"   "52900"  
 [897] "273000"  "2700000" "2350000" "213500"  "83285"   "112808"  "86940"   "118950" 
 [905] "150135"  "48000"   "1075000" "288000"  "434203"  "256050"  "267075"  "278700" 
 [913] "482893"  "184500"  "777777"  "1111111" "177900"  "1130000" "474000"  "80900"  
 [921] "184900"  "163510"  "147318"  "119404"  "124572"  "121575"  "94500"   "169149" 
 [929] "114629"  "106754"  "70067"   "122348"  "69008"   "252595"  "172044"  "184375" 
 [937] "215763"  "130921"  "174699"  "187500"  "93636"   "197701"  "106400"  "197975" 
 [945] "23500"   "44000"   "849000"  "118800"  "77292"   "75190"   "55600"   "90931"  
 [953] "112750"  "121900"  "89100"   "154500"  "134700"  "930000"  "169100"  "198300" 
 [961] "177800"  "181700"  "101200"  "113454"  "131500"  "168500"  "200485"  "196500" 
 [969] "151500"  "263000"  "149800"  "249600"  "362300"  "247100"  "285400"  "366000" 
 [977] "232500"  "231200"  "213000"  "169990"  "150500"  "180800"  "172500"  "121500" 
 [985] "53000"   "137800"  "167424"  "373000"  "418000"  "2200000" "800000"  "472500" 
 [993] "328000"  "310300"  "327100"  "999999"  "542800"  "564500"  "312300"  "547600" 
 [ reached getOption("max.print") -- omitted 1417 entries ]

#price alta variabilidad, dado que es una variable numérica, 
#se podría transformar en categórica revisando más a fondo los valores
summary(as.integer(uniqueValues$price))

    Min.  1st Qu.   Median     Mean  3rd Qu.     Max. 
    6000   104106   158032   335764   296500 23456789 

#Tipo de propiedad
uniqueValues$property_type

[1] "PH"           "Casa"         "Departamento"

#Las tres gategorías filtradas del dataset: PH, Casa, Departamento

#surface_total y surface_covered alta variabilidad, dado que es una variable numérica, #se podría transformar en categórica revisando más a fondo los valores

summary(as.integer(uniqueValues$surface_total))

    Min.  1st Qu.   Median     Mean  3rd Qu.     Max.     NA's 
     0.0    145.2    279.5    749.6    450.8 126062.0        1 

summary(as.integer(uniqueValues$surface_covered))

    Min.  1st Qu.   Median     Mean  3rd Qu.     Max.     NA's 
     1.0    120.8    236.5    719.7    374.2 126062.0        1 

#Price
uniqueValues$price

   [1] "320000"  "500000"  "350000"  "470000"  "155000"  "199900"  "147000"  "92294"  
   [9] "115000"  "77000"   "88900"   "88798"   "110975"  "92943"   "69000"   "99000"  
  [17] "96984"   "125000"  "99500"   "121600"  "285000"  "150000"  "140000"  "110000" 
  [25] "96000"   "248200"  "152732"  "310000"  "108000"  "94800"   "1080000" "88000"  
  [33] "225000"  "85000"   "129900"  "185000"  "158000"  "98000"   "80000"   "159900" 
  [41] "87000"   "178000"  "172000"  "208000"  "83000"   "134000"  "135000"  "105000" 
  [49] "165000"  "90000"   "104500"  "119000"  "192000"  "390000"  "169000"  "86000"  
  [57] "79000"   "315000"  "230000"  "120000"  "259000"  "180000"  "269900"  "190000" 
  [65] "175000"  "130000"  "209000"  "270000"  "340000"  "194500"  "255000"  "139000" 
  [73] "439000"  "729000"  "128000"  "101000"  "92000"   "245000"  "214900"  "200000" 
  [81] "385000"  "370000"  "220000"  "189000"  "239000"  "260000"  "252000"  "290000" 
  [89] "790000"  "595000"  "280000"  "195000"  "613567"  "215000"  "210000"  "580000" 
  [97] "224000"  "850000"  "680000"  "1115000" "900000"  "250000"  "199000"  "249000" 
 [105] "94000"   "95000"   "70000"   "65000"   "795000"  "325000"  "182000"  "183000" 
 [113] "380000"  "770000"  "68000"   "84000"   "160000"  "100700"  "102000"  "168000" 
 [121] "855000"  "865000"  "485000"  "780000"  "75000"   "106000"  "142000"  "235000" 
 [129] "510000"  "103000"  "98500"   "104000"  "187300"  "123900"  "128400"  "85600"  
 [137] "80400"   "193000"  "195200"  "126400"  "92400"   "191200"  "136500"  "305000" 
 [145] "720000"  "107000"  "74000"   "54900"   "109000"  "145000"  "143000"  "116000" 
 [153] "204000"  "100000"  "239800"  "93000"   "205000"  "138000"  "112000"  "360000" 
 [161] "124000"  "170000"  "84102"   "127000"  "111000"  "173000"  "217000"  "152000" 
 [169] "149000"  "286000"  "995000"  "275000"  "206700"  "490000"  "268000"  "295000" 
 [177] "460000"  "650000"  "980000"  "440000"  "384000"  "450000"  "1700000" "397000" 
 [185] "550000"  "620000"  "184000"  "1850000" "1650000" "375000"  "540000"  "1300000"
 [193] "1970000" "1250000" "399000"  "628000"  "1150000" "1350000" "1600000" "297000" 
 [201] "278000"  "332000"  "133000"  "479000"  "365000"  "355000"  "240000"  "649000" 
 [209] "420000"  "236000"  "264000"  "300000"  "749000"  "84500"   "69500"   "97800"  
 [217] "415000"  "73000"   "82000"   "132000"  "138500"  "419000"  "1200000" "64900"  
 [225] "445000"  "359500"  "239500"  "206000"  "282000"  "118000"  "89000"   "198000" 
 [233] "129000"  "78000"   "299000"  "111900"  "192900"  "64000"   "318000"  "174000" 
 [241] "157354"  "108286"  "99900"   "219000"  "42000"   "329000"  "895000"  "149500" 
 [249] "157800"  "137000"  "520000"  "1100000" "144900"  "398000"  "124999"  "157500" 
 [257] "117000"  "378000"  "191911"  "289000"  "37000"   "345000"  "518000"  "83500"  
 [265] "395000"  "430000"  "269000"  "49000"   "114000"  "99800"   "114500"  "90500"  
 [273] "128500"  "241500"  "62000"   "203788"  "211011"  "194400"  "45000"   "95266"  
 [281] "85178"   "93989"   "95832"   "88372"   "93374"   "83370"   "92479"   "87341"  
 [289] "98428"   "91602"   "98930"   "90040"   "90766"   "91707"   "99518"   "84274"  
 [297] "94192"   "89054"   "101360"  "86106"   "89770"   "97098"   "102214"  "100762" 
 [305] "94474"   "97675"   "85037"   "90857"   "92146"   "86705"   "95904"   "97192"  
 [313] "100321"  "85629"   "83916"   "104106"  "81703"   "95809"   "96535"   "94642"  
 [321] "141000"  "159000"  "55000"   "103300"  "89900"   "135300"  "284000"  "97000"  
 [329] "170052"  "162400"  "330000"  "123000"  "84900"   "368000"  "314200"  "410000" 
 [337] "144500"  "177000"  "302797"  "276404"  "288569"  "277564"  "97500"   "244290" 
 [345] "162505"  "248081"  "203000"  "67500"   "88500"   "212500"  "159500"  "79900"  
 [353] "670000"  "298000"  "572000"  "404000"  "126900"  "239999"  "1000000" "232000" 
 [361] "480000"  "364000"  "400000"  "186000"  "353000"  "335000"  "307000"  "265000" 
 [369] "342000"  "218000"  "227000"  "228000"  "279900"  "242000"  "149600"  "169900" 
 [377] "254000"  "153000"  "235500"  "52000"   "176000"  "179000"  "189900"  "575000" 
 [385] "249999"  "154900"  "744000"  "886000"  "349000"  "449900"  "387000"  "590000" 
 [393] "549000"  "212000"  "304500"  "495000"  "920000"  "3500000" "515000"  "750000" 
 [401] "3400000" "690000"  "640000"  "698000"  "880000"  "565000"  "598000"  "144000" 
 [409] "156000"  "194900"  "95500"   "237000"  "156960"  "294000"  "162000"  "72000"  
 [417] "160125"  "59900"   "95200"   "109500"  "119500"  "113000"  "35000"   "475000" 
 [425] "125900"  "173583"  "99100"   "122500"  "372000"  "168900"  "226000"  "630000" 
 [433] "163000"  "350550"  "279000"  "493000"  "449000"  "309000"  "57900"   "870000" 
 [441] "563000"  "194000"  "319000"  "465000"  "615000"  "229000"  "2550000" "3700000"
 [449] "1480000" "940000"  "860000"  "359100"  "448000"  "343000"  "719000"  "444000" 
 [457] "828000"  "455000"  "267000"  "524000"  "148000"  "435000"  "2900000" "950000" 
 [465] "4500000" "675000"  "530000"  "560000"  "47000"   "425000"  "93500"   "58174"  
 [473] "75542"   "98280"   "95280"   "730000"  "187000"  "570000"  "122000"  "157000" 
 [481] "145600"  "149900"  "825000"  "1140000" "1400000" "1050000" "625000"  "164000" 
 [489] "60000"   "890000"  "427696"  "712000"  "85720"   "133849"  "59000"   "106800" 
 [497] "119700"  "116800"  "118600"  "114800"  "102700"  "113800"  "76000"   "313000" 
 [505] "74500"   "745900"  "84501"   "120150"  "197860"  "190250"  "115700"  "119900" 
 [513] "185080"  "103320"  "50000"   "89999"   "73900"   "186600"  "133500"  "105100" 
 [521] "597000"  "158900"  "136422"  "803648"  "627880"  "129294"  "2169696" "69900"  
 [529] "127800"  "60500"   "64800"   "105948"  "99573"   "148300"  "106948"  "133900" 
 [537] "156890"  "76900"   "164198"  "248000"  "635000"  "229900"  "164600"  "147500" 
 [545] "199500"  "202375"  "233000"  "229500"  "367000"  "158500"  "158250"  "217500" 
 [553] "177600"  "279500"  "166000"  "39500"   "37500"   "216000"  "289100"  "244900" 
 [561] "4000000" "224900"  "287000"  "369000"  "897000"  "1500000" "1550000" "1800000"
 [569] "1380000" "223000"  "4800000" "2800000" "351000"  "845000"  "660000"  "699000" 
 [577] "1680000" "188000"  "87749"   "257000"  "189500"  "202566"  "198432"  "210834" 
 [585] "215488"  "214968"  "45900"   "166600"  "90800"   "81000"   "2345678" "124500" 
 [593] "167000"  "316484"  "262000"  "126825"  "139500"  "131100"  "110600"  "1234567"
 [601] "121000"  "74900"   "56000"   "169500"  "134800"  "109900"  "61000"   "80047"  
 [609] "77553"   "77500"   "89800"   "346000"  "1030000" "559000"  "591361"  "558571" 
 [617] "68500"   "75500"   "65500"   "72500"   "85500"   "79500"   "64500"   "71000"  
 [625] "89500"   "66500"   "73500"   "43000"   "63000"   "76500"   "58500"   "82500"  
 [633] "62500"   "80500"   "92500"   "56500"   "59500"   "70500"   "91650"   "101050" 
 [641] "725000"  "104436"  "115788"  "64212"   "118463"  "44592"   "69258"   "67241"  
 [649] "92818"   "90804"   "47294"   "61993"   "134725"  "156188"  "55517"   "58237"  
 [657] "49135"   "136000"  "66000"   "112400"  "138600"  "153500"  "201500"  "66900"  
 [665] "83800"   "133575"  "147275"  "193500"  "122900"  "86130"   "101039"  "181140" 
 [673] "148200"  "109800"  "102573"  "93600"   "104948"  "64950"   "990000"  "1390000"
 [681] "1340000" "184300"  "272000"  "174900"  "119990"  "389000"  "496000"  "228542" 
 [689] "387090"  "359000"  "292000"  "249500"  "238000"  "452000"  "1360000" "1450000"
 [697] "260850"  "459000"  "545000"  "519000"  "3000000" "1099000" "296000"  "128900" 
 [705] "535000"  "80711"   "79120"   "371000"  "81900"   "32000"   "102526"  "102481" 
 [713] "104311"  "112587"  "87500"   "39000"   "104900"  "67000"   "179500"  "126000" 
 [721] "442650"  "476700"  "499800"  "284997"  "374000"  "695000"  "408400"  "196000" 
 [729] "314000"  "151000"  "882700"  "781820"  "819650"  "807040"  "794430"  "197000" 
 [737] "258000"  "321000"  "1750000" "338000"  "910000"  "318200"  "738400"  "875000" 
 [745] "555000"  "423300"  "91500"   "998000"  "428000"  "243000"  "154000"  "389500" 
 [753] "68100"   "108500"  "129500"  "73600"   "108700"  "79200"   "60200"   "106600" 
 [761] "27900"   "175800"  "139900"  "110900"  "399900"  "124900"  "211000"  "915000" 
 [769] "166900"  "327000"  "610000"  "1620000" "3089000" "2490000" "700000"  "1195000"
 [777] "1440000" "1545000" "1730000" "69800"   "138900"  "86500"   "247000"  "57000"  
 [785] "405000"  "142900"  "91900"   "85900"   "180380"  "151287"  "209500"  "131990" 
 [793] "339000"  "115900"  "82900"   "184980"  "179900"  "214000"  "183400"  "49900"  
 [801] "599000"  "1490000" "348000"  "1950000" "51500"   "144800"  "159300"  "145800" 
 [809] "289500"  "159700"  "134900"  "241400"  "830000"  "186070"  "86600"   "114900" 
 [817] "476000"  "91000"   "26500"   "191990"  "124990"  "106150"  "100760"  "1395000"
 [825] "1604320" "129981"  "106900"  "97900"   "122845"  "110935"  "94900"   "202000" 
 [833] "265500"  "390250"  "407000"  "710000"  "394000"  "498000"  "685000"  "112500" 
 [841] "336000"  "261000"  "277000"  "2500000" "2300000" "960000"  "1090000" "166400" 
 [849] "107900"  "78500"   "131000"  "141050"  "100580"  "73295"   "94160"   "125653" 
 [857] "118500"  "357000"  "698900"  "975000"  "760000"  "58000"   "255982"  "95770"  
 [865] "201370"  "134016"  "101516"  "108216"  "139454"  "103695"  "102215"  "105216" 
 [873] "89700"   "100070"  "140003"  "148539"  "146078"  "126246"  "142473"  "145212" 
 [881] "134006"  "136016"  "55500"   "79600"   "71662"   "319500"  "712600"  "379000" 
 [889] "79750"   "73402"   "80892"   "74965"   "76560"   "78155"   "81345"   "52900"  
 [897] "273000"  "2700000" "2350000" "213500"  "83285"   "112808"  "86940"   "118950" 
 [905] "150135"  "48000"   "1075000" "288000"  "434203"  "256050"  "267075"  "278700" 
 [913] "482893"  "184500"  "777777"  "1111111" "177900"  "1130000" "474000"  "80900"  
 [921] "184900"  "163510"  "147318"  "119404"  "124572"  "121575"  "94500"   "169149" 
 [929] "114629"  "106754"  "70067"   "122348"  "69008"   "252595"  "172044"  "184375" 
 [937] "215763"  "130921"  "174699"  "187500"  "93636"   "197701"  "106400"  "197975" 
 [945] "23500"   "44000"   "849000"  "118800"  "77292"   "75190"   "55600"   "90931"  
 [953] "112750"  "121900"  "89100"   "154500"  "134700"  "930000"  "169100"  "198300" 
 [961] "177800"  "181700"  "101200"  "113454"  "131500"  "168500"  "200485"  "196500" 
 [969] "151500"  "263000"  "149800"  "249600"  "362300"  "247100"  "285400"  "366000" 
 [977] "232500"  "231200"  "213000"  "169990"  "150500"  "180800"  "172500"  "121500" 
 [985] "53000"   "137800"  "167424"  "373000"  "418000"  "2200000" "800000"  "472500" 
 [993] "328000"  "310300"  "327100"  "999999"  "542800"  "564500"  "312300"  "547600" 
 [ reached getOption("max.print") -- omitted 1417 entries ]

#price alta variabilidad, dado que es una variable numérica, #se podría transformar en categórica revisando más a fondo los valores

summary(as.integer(uniqueValues$price))

    Min.  1st Qu.   Median     Mean  3rd Qu.     Max. 
    6000   104106   158032   335764   296500 23456789 

#Tipo de propiedad

uniqueValues$property_type

[1] "PH"           "Casa"         "Departamento"

#Las tres gategorías filtradas del dataset: PH, Casa, Departamento

#a.Obtener la cantidad de valores unicos y de valores faltantes (NAs) para cada una de estas variables #Ahora vamos a totalizar los valores faltantes por columnap para esto usamos la función apply para sumar #sobre los resultados de la misma función para listar los is.na por columna #inceptionTime

apply(apply(ar_properties_filtrado,2,is.na),2,sum)

             id              l3           rooms        bedrooms       bathrooms 
              0             136            1975            9861            1211 
  surface_total surface_covered           price   property_type 
           1444            1174               0               0 

#b.Obtener la matriz de correlacion para las variables numericas. #Para las correlaciones usaremos la librería corrr

library(tidyverse)
library(corrr)
library(corrplot)

corrplot 0.84 loaded

#Separaremos las variables numéricas

numeric_variables <-  ar_properties_filtrado %>% 
  select(rooms, bedrooms, bathrooms, surface_total, surface_covered, price)
glimpse(numeric_variables)

Observations: 24,323
Variables: 6
$ rooms           <fct> NA, 6, NA, 3, NA, 3, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 3,...
$ bedrooms        <fct> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N...
$ bathrooms       <fct> NA, 2, 2, 4, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 1...
$ surface_total   <fct> 300, 178, 240, 157, 140, 95, 44, 40, 49, 40, 40, 40, 49, 40, 23, ...
$ surface_covered <fct> 180, 240, 157, NA, 110, 69, 38, 37, 44, 37, 37, 37, 44, 37, 23, 3...
$ price           <fct> 320000, 500000, 350000, 470000, 155000, 199900, 147000, 92294, 11...

#Transformamos las variables categóricas en numéricas

numeric_variables <- apply(apply(numeric_variables,2,as.character), 2, as.numeric)
crm <- cor(numeric_variables, use="complete.obs", method="pearson") 
crm

                     rooms   bedrooms  bathrooms surface_total surface_covered      price
rooms           1.00000000 0.92979527 0.60318421    0.06364667      0.05561538 0.47595400
bedrooms        0.92979527 1.00000000 0.61396803    0.06507773      0.05684364 0.42622405
bathrooms       0.60318421 0.61396803 1.00000000    0.05664833      0.05071377 0.59618271
surface_total   0.06364667 0.06507773 0.05664833    1.00000000      0.98901389 0.04477758
surface_covered 0.05561538 0.05684364 0.05071377    0.98901389      1.00000000 0.04006500
price           0.47595400 0.42622405 0.59618271    0.04477758      0.04006500 1.00000000

#Generámos la matriz de corelaciones

library(RColorBrewer)
library(corrplot)
n <- ncol(crm)
p.mat<- matrix(NA, n, n)
col <- colorRampPalette(c("#BB4444", "#EE9988", "#FFFFFF", "#77AADD", "#4477AA"))
corrplot(crm, method="color", col=col(200),  
         type="upper", order="hclust", 
         addCoef.col = "black", # Add coefficient of correlation
         tl.col="black", tl.srt=45, #Text label color and rotation
         # Combine with significance
         p.mat = p.mat, sig.level = 0.01, insig = "blank", 
         # hide correlation coefficient on the principal diagonal
         diag=FALSE 
)

#Encontramos que: #Todas las correlaciones entre las varialbes son positivas. #Contra la hipótesis inicial no se observa una correlaciónmarcada entre la superficie cubierta y el precio #Se observauna correlaciónentre el precio y el número de baños y cuartos

#3.Preparacion de los datos (II) #a.En el punto 2 deberian haber encontrado que la variable bedrooms presenta una alta #proporción de valores faltantes y que presenta una fuerte correlacion con la variable rooms. #Por lo tanto, vamos a eliminarla. #Nota: surface_total y surface_covered también están estrechamente correlacionadas

ar_properties_filtrado <- ar_properties_filtrado %>% select(-bedrooms)

#b.Eliminar todos los registros que presentan valores faltantes #Para esto usaremos la función drop_na de tidyr

#4.Analisis exploratorios (II) #a.Obtener estadisticas descriptivas para la variable precio (cuartiles, promedio, minimo y maximo) y #realizar un histograma de la variable

summaryPrecio <- summary(as.numeric(as.character(ar_properties_filtrado$price)))
summaryPrecio

   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
   6000  117000  169000  250258  270000 6000000 

priceHistogram <- qplot(as.numeric(as.character(ar_properties_filtrado$price)),
                        geom="histogram",
                        main = "Histograma de precios",
                        xlab = "Precio",
                        bins = 500) 
priceHistogram

#Como vemos el histograma se ve algo distorsionado por los valores extremos que tiene #la variable price

#b.Obtener estadisticas descriptivas para la variable precio #(cuartiles, promedio, minimo y maximo) por cada tipo de propiedad.

summaryPrecioPorTipo <- summary(as.numeric(as.character(ar_properties_filtrado$price)))
summaryPrecioPorTipo <- tapply(as.numeric(as.character(ar_properties_filtrado$price)),
                              ar_properties_filtrado$property_type, summary)
summaryPrecioPorTipo <- summaryPrecioPorTipo[c("PH","Departamento","Casa")]
summaryPrecioPorTipo

$PH
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
  42000  134450  189000  215670  270000 1200000 

$Departamento
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
   6000  114000  163000  246667  260762 6000000 

$Casa
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
  62900  240000  335000  427946  499225 5000000 

#c.Realizar un grafico de boxplot de la variable precio por tipo de propiedad

ar_properties_filtrado$price <- as.numeric(as.character(ar_properties_filtrado$price)) 
ggplot(ar_properties_filtrado, mapping = aes(x = property_type, y = price,
                                   group = property_type, fill = property_type )) +
                                   geom_boxplot()

#Una vez más los outliers no nos permiten ver muy bien la comparación entre los boxplots

#d.Realizar un correlagrama usando GGally

library(GGally)

Registered S3 method overwritten by 'GGally':
  method from   
  +.gg   ggplot2

Attaching package: 㤼㸱GGally㤼㸲

The following object is masked from 㤼㸱package:dplyr㤼㸲:

    nasa

ggallyData <- ar_properties_filtrado %>% select(rooms, bathrooms, surface_total,
                                                surface_covered, price, property_type)
ggallyData$rooms <- as.numeric(as.character(ggallyData$rooms))
ggallyData$bathrooms <- as.numeric(as.character(ggallyData$bathrooms))
ggallyData$surface_total <- as.numeric(as.character(ggallyData$surface_total))
ggallyData$surface_covered <- as.numeric(as.character(ggallyData$surface_covered))
ggallyData$property_type <- as.factor(as.character(ggallyData$property_type))
levels(ggallyData$property_type)

[1] "Casa"         "Departamento" "PH"          

#Departamento 17598 -414 #PH 1831 -414 #Casa 712 -414

ggpairs(ggallyData,  mapping = aes(color = (ggallyData$property_type)))

 plot: [1,1] [==--------------------------------------------------------------]  3% est: 0s 
 plot: [1,2] [====------------------------------------------------------------]  6% est:22s 
 plot: [1,3] [=====-----------------------------------------------------------]  8% est:19s 
 plot: [1,4] [=======---------------------------------------------------------] 11% est:21s 
 plot: [1,5] [=========-------------------------------------------------------] 14% est:18s 
 plot: [1,6] [===========-----------------------------------------------------] 17% est:17s 
 plot: [2,1] [============----------------------------------------------------] 19% est:18s 
 plot: [2,2] [==============--------------------------------------------------] 22% est:19s 
 plot: [2,3] [================------------------------------------------------] 25% est:19s 
 plot: [2,4] [==================----------------------------------------------] 28% est:17s 
 plot: [2,5] [====================--------------------------------------------] 31% est:16s 
 plot: [2,6] [=====================-------------------------------------------] 33% est:15s 
 plot: [3,1] [=======================-----------------------------------------] 36% est:15s 
 plot: [3,2] [=========================---------------------------------------] 39% est:15s 
 plot: [3,3] [===========================-------------------------------------] 42% est:14s 
 plot: [3,4] [============================------------------------------------] 44% est:14s 
 plot: [3,5] [==============================----------------------------------] 47% est:13s 
 plot: [3,6] [================================--------------------------------] 50% est:12s 
 plot: [4,1] [==================================------------------------------] 53% est:11s 
 plot: [4,2] [====================================----------------------------] 56% est:11s 
 plot: [4,3] [=====================================---------------------------] 58% est:10s 
 plot: [4,4] [=======================================-------------------------] 61% est:10s 
 plot: [4,5] [=========================================-----------------------] 64% est: 9s 
 plot: [4,6] [===========================================---------------------] 67% est: 8s 
 plot: [5,1] [============================================--------------------] 69% est: 7s 
 plot: [5,2] [==============================================------------------] 72% est: 7s 
 plot: [5,3] [================================================----------------] 75% est: 6s 
 plot: [5,4] [==================================================--------------] 78% est: 5s 
 plot: [5,5] [====================================================------------] 81% est: 5s 
 plot: [5,6] [=====================================================-----------] 83% est: 4s 
 plot: [6,1] [=======================================================---------] 86% est: 3s 
 plot: [6,2] [=========================================================-------] 89% est: 3s 
 plot: [6,3] [===========================================================-----] 92% est: 2s 
 plot: [6,4] [============================================================----] 94% est: 1s 
 plot: [6,5] [==============================================================--] 97% est: 1s 
 plot: [6,6] [================================================================]100% est: 0s 
                                                                                            

#5.Outliers #a.Eliminar los outliers de la variable precio con algún criterio que elijan. #Los mayores outliers de precio los encontramos en “Casa” y en “Departamento”. #Son outliers superiores en ambos casos, con lo que considero que lo más apropiado sería excluir #los valores que superen 3 distancias inter-cuartil sobre el 3 cuartil.

summaryPrecioPorTipo

$PH
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
  42000  134450  189000  215670  270000 1200000 

$Departamento
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
   6000  114000  163000  246667  260762 6000000 

$Casa
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
  62900  240000  335000  427946  499225 5000000 

#Si usamos Casa para calcular las distnacias intercuartil
interqDistance <- as.numeric(summaryPrecioPorTipo$Casa[5] - summaryPrecioPorTipo$Casa[3])
interqDistance

[1] 164225

#Si usamos Departamento para calcular las distnacias intercuartil
interqDistance <- as.numeric(summaryPrecioPorTipo$Departamento[5] - summaryPrecioPorTipo$Departamento[3])
interqDistance

[1] 97762.5

#Usaremos Departamento, dado que el volumen de datos es muhco mayor para propiedades de este tipo. #Se realizaron experimentos también usando casa, pero el filtro no era tan efectivo como se esperaba.

filter <- as.numeric((interqDistance*3) + summaryPrecioPorTipo$Departamento[5])
filter

[1] 554050

ggallyDataNoOutliers <- ggallyData %>% filter(ggallyData$price <= filter)

#Con esto filtramos un outlier de superficie para un PH que dificulta ver las gráficas

ggallyDataNoOutliers <- ggallyDataNoOutliers %>% filter(ggallyDataNoOutliers$surface_covered < 11000)
summary(ggallyDataNoOutliers)

     rooms          bathrooms     surface_total     
 Min.   : 1.000   Min.   : 1.00   Min.   :   12.00  
 1st Qu.: 2.000   1st Qu.: 1.00   1st Qu.:   44.00  
 Median : 3.000   Median : 1.00   Median :   62.00  
 Mean   : 2.638   Mean   : 1.38   Mean   :   84.78  
 3rd Qu.: 3.000   3rd Qu.: 2.00   3rd Qu.:   94.00  
 Max.   :12.000   Max.   :14.00   Max.   :16725.00  
 surface_covered        price             property_type  
 Min.   :    3.00   Min.   :  6000   Casa        :  576  
 1st Qu.:   40.00   1st Qu.:114000   Departamento:16347  
 Median :   55.00   Median :160000   PH          : 1800  
 Mean   :   72.53   Mean   :191495                       
 3rd Qu.:   80.00   3rd Qu.:245000                       
 Max.   :10145.00   Max.   :550000                       

#El filtro aplicado permite mucha más claridad en los boxplot de precio, además de mayor claridad #en los gráficos de rooms y de bathrooms, puesto que excluye valores de ouliers extremos que allí se tenían.

#Analisis exploratorios (III) #a.Obtener estadisticas descriptivas para la variable precio (cuartiles, promedio, minimo y maximo) y realizar un histograma de la variable

summaryPrecioFiltrado <- summary(as.numeric(as.character(ggallyDataNoOutliers$price)))
summaryPrecioFiltrado

   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
   6000  114000  160000  191495  245000  550000 

#El nuevo valormáxmo es $ 550.000es mucho menor que el valor que se tenía antes, sin embargo #es el resultado de expcluir los outliers extremos

priceHistogramFiltrado <- qplot(as.numeric(as.character(ggallyDataNoOutliers$price)),
                        geom="histogram",
                        main = "Histograma de precios",
                        xlab = "Precio",
                        bins = 500) 
priceHistogramFiltrado

#El histograma de precios es más claro ahora,se mantiene eso si, siendo una distribucion con cola #a la derecha

#b.Obtener estadisticas descriptivas para la variable precio (cuartiles, promedio, minimo y maximo) por cada tipo de propiedad.

summaryPrecioPorTipoFiltrado <- summary(as.numeric(as.character(ggallyDataNoOutliers$price)))
summaryPrecioPorTipoFiltrado <- tapply(as.numeric(as.character(ggallyDataNoOutliers$price)),
                                       ggallyDataNoOutliers$property_type, summary)
summaryPrecioPorTipoFiltrado <- summaryPrecioPorTipoFiltrado[c("PH","Departamento","Casa")]
summaryPrecioPorTipoFiltrado

$PH
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
  42000  133000  187250  207549  265000  550000 

$Departamento
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
   6000  110000  155000  185661  234950  550000 

$Casa
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
  62900  220000  290000  306892  395000  550000 

#La media más alta sigue estando para los casos de las casas. Los PH y los Departamentos tienen #medias muy similares #c.Realizar un grafico de boxplot de la variable precio por tipo de propiedad

ggallyDataNoOutliers$price <- as.numeric(as.character(ggallyDataNoOutliers$price)) 
ggplot(ggallyDataNoOutliers, mapping = aes(x = property_type, y = price,
                                         group = property_type, fill = property_type )) +
                                         geom_boxplot()

#EL boxplot refleja valores superiores en general para el caso de las casas (puede darse debido a #su tamañoen metros cuadrados y a su mayor cantidad de ambientes) #d.Realizar un correlagrama usando GGAlly

ggpairs(ggallyDataNoOutliers,  mapping = aes(color = (ggallyDataNoOutliers$property_type)))

 plot: [1,1] [=--------------------------------------]  3% est: 0s 
 plot: [1,2] [==-------------------------------------]  6% est:19s 
 plot: [1,3] [===------------------------------------]  8% est:19s 
 plot: [1,4] [====-----------------------------------] 11% est:17s 
 plot: [1,5] [=====----------------------------------] 14% est:16s 
 plot: [1,6] [======---------------------------------] 17% est:15s 
 plot: [2,1] [========-------------------------------] 19% est:17s 
 plot: [2,2] [=========------------------------------] 22% est:18s 
 plot: [2,3] [==========-----------------------------] 25% est:17s 
 plot: [2,4] [===========----------------------------] 28% est:15s 
 plot: [2,5] [============---------------------------] 31% est:14s 
 plot: [2,6] [=============--------------------------] 33% est:13s 
 plot: [3,1] [==============-------------------------] 36% est:13s 
 plot: [3,2] [===============------------------------] 39% est:13s 
 plot: [3,3] [================-----------------------] 42% est:12s 
 plot: [3,4] [=================----------------------] 44% est:12s 
 plot: [3,5] [==================---------------------] 47% est:11s 
 plot: [3,6] [====================-------------------] 50% est:10s 
 plot: [4,1] [=====================------------------] 53% est:10s 
 plot: [4,2] [======================-----------------] 56% est: 9s 
 plot: [4,3] [=======================----------------] 58% est: 9s 
 plot: [4,4] [========================---------------] 61% est: 9s 
 plot: [4,5] [=========================--------------] 64% est: 8s 
 plot: [4,6] [==========================-------------] 67% est: 7s 
 plot: [5,1] [===========================------------] 69% est: 7s 
 plot: [5,2] [============================-----------] 72% est: 6s 
 plot: [5,3] [=============================----------] 75% est: 6s 
 plot: [5,4] [==============================---------] 78% est: 5s 
 plot: [5,5] [===============================--------] 81% est: 4s 
 plot: [5,6] [================================-------] 83% est: 4s 
 plot: [6,1] [==================================-----] 86% est: 3s 
 plot: [6,2] [===================================----] 89% est: 3s 
 plot: [6,3] [====================================---] 92% est: 2s 
 plot: [6,4] [=====================================--] 94% est: 1s 
 plot: [6,5] [======================================-] 97% est: 1s 
 plot: [6,6] [=======================================]100% est: 0s 
                                                                   

#El correlograma nos muestra menos correlación enrte las variables precio y cantidad de baños, #curiosamente no se ve una correlacion entre la superficie y el precio, vemos el precio mas #relacionado con la cantidad de baños y con la cantidad de habitaciones

#7.Modelo lineal #a. Realizar un modelo lineal simple para explicar el precio en función de las habitaciones (rooms) #y otro modelo que explique el precio en función de la superficie total (surface_total)

#Añadimos las librerías necesarias:
library(modelr)
library(broom)

Attaching package: 㤼㸱broom㤼㸲

The following object is masked from 㤼㸱package:modelr㤼㸲:

    bootstrap

#Iniciamos con el modelo para las habitaciones

modeloRooms <- lm(rooms ~ price, data = ggallyDataNoOutliers)
ggallyDataNoOutliers %>% 
  add_predictions(modeloRooms) %>%
  ggplot(aes(price, pred)) + 
  geom_line() + 
  ggtitle(expression(beta[0] + beta[1]*x))

glance(modeloRooms)

ggallyDataNoOutliers %>% 
  add_residuals(modeloRooms) %>% 
  ggplot(aes(price, resid)) + 
  geom_hline(yintercept = 0, colour = "white", size = 3) + 
  geom_line() + 
  ggtitle(expression(+ epsilon))

#Los residuos no siguen un patrón definido que es lo que estábamos esperando #Ahora hacemos el modelo a partir de la superficie total

modeloSurface <- lm(surface_total ~ price, data = ggallyDataNoOutliers)
ggallyDataNoOutliers %>% 
  add_predictions(modeloSurface) %>%
  ggplot(aes(price, pred)) + 
  geom_line() + 
  ggtitle(expression(beta[0] + beta[1]*x))

glance(modeloSurface)

ggallyDataNoOutliers %>% 
  add_residuals(modeloSurface) %>% 
  ggplot(aes(price, resid)) + 
  geom_hline(yintercept = 0, colour = "white", size = 3) + 
  geom_line() + 
  ggtitle(expression(+ epsilon))

#b. Usar la función summary() para obtener informacion de ambos modelos. Explicar los valores de los coeficientes estimados.

summary(modeloRooms)

Call:
lm(formula = rooms ~ price, data = ggallyDataNoOutliers)

Residuals:
    Min      1Q  Median      3Q     Max 
-4.0629 -0.7241 -0.0343  0.5977  8.5227 

Coefficients:
             Estimate Std. Error t value Pr(>|t|)    
(Intercept) 1.203e+00  1.456e-02   82.65   <2e-16 ***
price       7.494e-06  6.675e-08  112.28   <2e-16 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.9533 on 18721 degrees of freedom
Multiple R-squared:  0.4024,    Adjusted R-squared:  0.4024 
F-statistic: 1.261e+04 on 1 and 18721 DF,  p-value: < 2.2e-16

summary(modeloSurface)

Call:
lm(formula = surface_total ~ price, data = ggallyDataNoOutliers)

Residuals:
    Min      1Q  Median      3Q     Max 
 -138.9   -22.7   -12.9    -0.6 16602.1 

Coefficients:
             Estimate Std. Error t value Pr(>|t|)    
(Intercept) 1.752e+01  3.522e+00   4.974 6.63e-07 ***
price       3.512e-04  1.615e-05  21.746  < 2e-16 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 230.7 on 18721 degrees of freedom
Multiple R-squared:  0.02464,   Adjusted R-squared:  0.02459 
F-statistic: 472.9 on 1 and 18721 DF,  p-value: < 2.2e-16

#c. ¿Cuál modelo usarían para predecir el precio? ¿Por qué? #Respecto a los resultados de la función Sumary preferiría quedarme con el modelo por #habitaciones, tiene un R-Square mucho más alto que el modelo de superficie, y un error estandrd #muchísimo menor.